Generative model with whiteboard

Abstract

A computing system is provided, including processing circuitry configured to cause an interaction interface for a trained generative model to be presented, in which the interaction interface is configured to communicate a portion of a user interaction history. The processing circuitry is further configured to receive, via the interaction interface, an input for the trained generative model to generate an output. The processing circuitry is further configured to send a command to create, via the trained generative model or another trained generative model, a whiteboard based on the user interaction history and receive the created whiteboard. The processing circuitry is further configured to generate a prompt based on the whiteboard and the instruction from the user and provide the prompt to the trained generative model. The processing circuitry is further configured to receive a response from the trained generative model and output the response via the interaction interface.

The invention claimed is: 
     
         1 . A computing system, comprising:
 processing circuitry configured to:
 cause an interaction interface for a trained generative model to be presented, the interaction interface being configured to communicate a portion of a user interaction history; 
 receive, via the interaction interface, an input for the trained generative model to generate an output to be included in the user interaction history; 
 send a command to create, via the trained generative model or another trained generative model, a whiteboard that includes information that is based on the output in the user interaction history; 
 receive the created whiteboard from the trained generative model or another trained generative model; 
 generate a prompt configured to be input to the trained generative model, the prompt including the whiteboard and an instruction from the user received via the interaction interface; 
 provide the prompt to the trained generative model; 
 receive, in response to the prompt, a response from the trained generative model; and 
 output the response via the interaction interface. 
   
     
     
         2 . The computing system of  claim 1 , wherein the processing circuitry is configured to create the whiteboard at least in part by (1) generating a whiteboard generation prompt including the user interaction history, and a whiteboard generation instruction, (2) passing the whiteboard generation prompt to the trained generative model or the another trained generative model, and (3) in response, receiving the whiteboard from the trained generative model or the another trained generative model. 
     
     
         3 . The computing system of  claim 2 , wherein the whiteboard generation prompt is generated to further include a prior version of the whiteboard, and the received whiteboard is an updated version of the whiteboard. 
     
     
         4 . The computing system of  claim 1 , wherein the processing circuitry is further configured to update the whiteboard based on the user interaction history including current exchanges between the user and the trained generative model. 
     
     
         5 . The computing system of  claim 4 , wherein the processing circuitry is further configured to archive the whiteboard in response to determining that a similarity between the whiteboard and the updated whiteboard exceeds a predetermined archiving similarity threshold. 
     
     
         6 . The computing system of  claim 5 , wherein the processing circuitry is further configured to retrieve and replace a current version of the whiteboard with an archived version of the whiteboard, in response to determining that a replace-with-archive condition is met. 
     
     
         7 . The computing system of  claim 1 , wherein the whiteboard is limited in size. 
     
     
         8 . The computing system of  claim 7 ,
 wherein the processing circuitry is configured to create the whiteboard at least in part by generating a whiteboard generation instruction, and   wherein the whiteboard generation instruction includes natural language text command to limit the whiteboard in size.   
     
     
         9 . The computing system of  claim 1 , wherein the processing circuitry is further configured to:
 generate a memory request including the context and the instruction; and   input the memory request into a semantic memory subsystem to retrieve one or more relevant memories from associated memory banks of the subsystem,   wherein the relevant memories are additionally included in the prompt passed to the trained generative model, and   wherein the whiteboard is not passed to the semantic memory subsystem.   
     
     
         10 . The computing system of  claim 1 , wherein
 the interaction interface includes a graphical user interface (GUI) that is configured to display the portion of the user interaction history, and   the input and the output are displayed in the GUI.   
     
     
         11 . A computerized method, comprising:
 causing an interaction interface for a trained generative model to be presented, the interaction interface being configured to communicate a portion of a user interaction history;   receiving, via the interaction interface, an input for the trained generative model to generate an output to be included in the user interaction history;   sending a command to create, via the trained generative model or another trained generative model, a whiteboard that includes information that is based on the output in the user interaction history;   receiving the created whiteboard from the trained generative model or another trained generative model;   generating a prompt configured to be input to the trained generative model, the prompt including the whiteboard and an instruction from the user received via the interaction interface;   providing the prompt to the trained generative model;   receiving, in response to the prompt, a response from the trained generative model; and   outputting the response via the interaction interface.   
     
     
         12 . The computerized method of  claim 11 , wherein the whiteboard is created at least in part by (1) generating a whiteboard generation prompt including the user interaction history, and a whiteboard generation instruction, (2) passing the whiteboard generation prompt to the trained generative model or the another trained generative model, and (3) in response, receiving the whiteboard from the trained generative model or the another trained generative model. 
     
     
         13 . The computerized method of  claim 12 , wherein the whiteboard generation prompt is generated to further include a prior version of the whiteboard, and the received whiteboard is an updated version of the whiteboard. 
     
     
         14 . The computerized method of  claim 11 , wherein the method further includes updating the whiteboard based on the user interaction history including current exchanges between the user and the trained generative model. 
     
     
         15 . The computerized method of  claim 11 , wherein the whiteboard generation instruction includes natural language text command to limit the whiteboard in size. 
     
     
         16 . The computerized method of  claim 11 , wherein the whiteboard is archived in response to determining that a similarity between the whiteboard and the updated whiteboard exceeds a predetermined archiving similarity threshold. 
     
     
         17 . The computerized method of  claim 16 , wherein a current version of the whiteboard is replaced with an archived version of the whiteboard, in response to determining that a replace-with-archive condition is met. 
     
     
         18 . The computerized method of  claim 11 , wherein
 the interaction interface includes a graphical user interface (GUI) that is configured to display the portion of the user interaction history, and   the input and the output are displayed in the GUI.   
     
     
         19 . A computing system, comprising:
 processing circuitry configured to:
 cause an interaction interface for a trained generative model to be presented, the interaction interface being configured to communicate a portion of a user interaction history; 
 receive, via the interaction interface, an input for the trained generative model to generate an output included in the user interaction history; 
 send a command to create, via the trained generative model or another trained generative model, a whiteboard that includes information that is based on the output in the user interaction history; 
 receive the created whiteboard from the trained generative model or another trained generative model; 
 update the whiteboard based on the user interaction history including current exchanges between the user and the trained generative model; and 
 archive the whiteboard in response to determining that a similarity between the whiteboard and the updated whiteboard exceeds a predetermined archiving similarity threshold. 
   
     
     
         20 . The computing system of  claim 19 , wherein the processing circuitry is further configured to retrieve and replace a current version of the whiteboard with an archived version of the whiteboard, in response to determining that a replace-with-archive condition is met.